Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     insign
    -0.07
     canh
    -0.07
    rowsable
    -0.07
     Semi
    -0.07
     www
    -0.07
    bac
    -0.07
    .nz
    -0.07
     '#{
    -0.06
     Arctic
    -0.06
    聊
    -0.06
    POSITIVE LOGITS
    337
    0.07
    administrator
    0.06
    czy
    0.06
    -led
    0.06
     constituent
    0.06
    sites
    0.06
    .PREFERRED
    0.06
    CED
    0.05
     없어
    0.05
    औ
    0.05
    Act Density 0.029%

    No Known Activations